Applied AI Engineer

Unify • San Francisco, CA

7d • $250,000 - $320,000

About The Position

Unify is building an AI-native outbound platform that helps revenue teams identify in-market buyers, enrich accounts using data from more than 40 sources, and execute personalized multichannel outreach. The Applied AI Engineer will develop new agent capabilities and build the production systems behind them, including planning, tool execution, context management, memory, and error recovery.

Working closely with product, design, and engineering, this role builds agents that research accounts, identify opportunities, and execute go-to-market workflows. The engineer will take features from prototype to customer use, then improve them using evaluations and real execution traces. The role also involves developing production AI systems and owning outcomes from early experiments through launch.

Requirements

• At least 3 years of software engineering experience.
• Hands-on experience shipping LLM applications or agents to production.
• Experience building systems with tool calling, multistep execution, and evaluations.
• Strong programming skills in TypeScript or Python.
• Experience building backend systems and integrating APIs.
• Comfort owning a feature across the stack.
• An empirical approach: define success, run experiments, inspect failures, and use evidence to guide decisions.
• Ability to translate high-level product ideas and customer problems into deployed solutions while balancing speed with sound engineering judgment.
• Initiative, adaptability, comfort with ambiguity, and collaborative working style.

Responsibilities

• Design and build agent harnesses, including execution loops, tool interfaces, context, and memory, so agents can complete complex workflows reliably.
• Turn ambiguous customer problems into working end-to-end features that connect agents to Unify’s data, integrations, and workflow infrastructure.
• Create evaluations based on real customer tasks and use execution traces and failure analysis to improve agent behavior.
• Own production reliability, latency, and cost; make long-running tasks resumable, handle tool failures, and provide users visibility and control over agent actions.
• Test models, prompting strategies, retrieval approaches, and orchestration patterns; measure their impact and incorporate effective approaches into the product.
• Build reusable tools and engineering practices that help the team ship faster, partnering with product and design to prioritize customer-impacting work.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level
• Education Level: No Education Listed